© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13616
    Prev
    Next
    INDEX
    Explanations

    SQL commands

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is find numeric values (numbers, measurements, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     життя
    0.60
    培養
    0.59
     samtidig
    0.56
    បត្តិ
    0.56
    ྒྱ
    0.55
     пості
    0.55
    ஞ்ஞான
    0.55
    <unused78>
    0.54
     জীবনের
    0.54
    лық
    0.54
    POSITIVE LOGITS
     where
    0.87
     경우에는
    0.78
     there
    0.77
     similarly
    0.66
    同様
    0.66
     जहां
    0.66
     ক্ষেত্রে
    0.66
    の場合は
    0.64
     false
    0.63
    where
    0.62
    Activations Density 0.223%

    No Known Activations